{"id":"https://openalex.org/W2165439482","doi":"https://doi.org/10.1145/1654059.1654096","title":"Minimizing communication in sparse matrix solvers","display_name":"Minimizing communication in sparse matrix solvers","publication_year":2009,"publication_date":"2009-11-14","ids":{"openalex":"https://openalex.org/W2165439482","doi":"https://doi.org/10.1145/1654059.1654096","mag":"2165439482"},"language":"en","primary_location":{"id":"doi:10.1145/1654059.1654096","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1654059.1654096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005444139","display_name":"Marghoob Mohiyuddin","orcid":null},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marghoob Mohiyuddin","raw_affiliation_strings":["University of California at Berkeley, CA and Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley, CA and Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071661180","display_name":"Mark Frederick Hoemmen","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hoemmen","raw_affiliation_strings":["University of California at Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076825233","display_name":"James Demmel","orcid":"https://orcid.org/0000-0003-1145-3745"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Demmel","raw_affiliation_strings":["University of California at Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091741596","display_name":"Katherine Yelick","orcid":"https://orcid.org/0000-0003-0957-701X"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine Yelick","raw_affiliation_strings":["University of California at Berkeley, CA and Lawrence Berkeley National Laboratory, Berkeley, CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Berkeley, CA and Lawrence Berkeley National Laboratory, Berkeley, CA","institution_ids":["https://openalex.org/I148283060"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":129,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7903464436531067},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7380212545394897},{"id":"https://openalex.org/keywords/generalized-minimal-residual-method","display_name":"Generalized minimal residual method","score":0.6235888600349426},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.6057131886482239},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.5151301622390747},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.5151249766349792},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4985086917877197},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.48911935091018677},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42487195134162903},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.4204506278038025},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4037162959575653},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.3197306990623474},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.2979387044906616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1623363494873047},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.14657291769981384},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.1201426088809967},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.08224955201148987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7903464436531067},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7380212545394897},{"id":"https://openalex.org/C155332342","wikidata":"https://www.wikidata.org/wiki/Q1432976","display_name":"Generalized minimal residual method","level":3,"score":0.6235888600349426},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.6057131886482239},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.5151301622390747},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.5151249766349792},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4985086917877197},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.48911935091018677},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42487195134162903},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4204506278038025},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4037162959575653},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.3197306990623474},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2979387044906616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1623363494873047},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.14657291769981384},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.1201426088809967},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.08224955201148987},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1654059.1654096","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1654059.1654096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Conference on High Performance Computing Networking, Storage and Analysis","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.160.3069","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.160.3069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bebop.cs.berkeley.edu/pubs/mohiyuddin-cagmres-sc09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W90336910","https://openalex.org/W110182411","https://openalex.org/W143824389","https://openalex.org/W1498251975","https://openalex.org/W1907157228","https://openalex.org/W1975714268","https://openalex.org/W1990832096","https://openalex.org/W2006651457","https://openalex.org/W2008698464","https://openalex.org/W2032052535","https://openalex.org/W2040425799","https://openalex.org/W2041519450","https://openalex.org/W2066692739","https://openalex.org/W2070232376","https://openalex.org/W2073061372","https://openalex.org/W2074361019","https://openalex.org/W2103877122","https://openalex.org/W2105745683","https://openalex.org/W2127022449","https://openalex.org/W2130289795","https://openalex.org/W2140153041","https://openalex.org/W2145194992","https://openalex.org/W2157237396","https://openalex.org/W2167868137","https://openalex.org/W2188450683","https://openalex.org/W6603689150"],"related_works":["https://openalex.org/W2026512611","https://openalex.org/W1985165680","https://openalex.org/W4245497162","https://openalex.org/W2353146130","https://openalex.org/W3000281689","https://openalex.org/W1990817968","https://openalex.org/W2150064838","https://openalex.org/W1933089384","https://openalex.org/W2781982188","https://openalex.org/W2185094550"],"abstract_inverted_index":{"Data":[0],"communication":[1,50,128],"within":[2],"the":[3,19,60,66,80,83,109,130],"memory":[4,61],"system":[5,17],"of":[6,34,56,73,82,97,119,142,154],"a":[7,16,35,54,71,104,123,139],"single":[8],"processor":[9],"node":[10],"and":[11,29,41,62,78,107],"between":[12],"multiple":[13],"nodes":[14],"in":[15,21,49,58],"is":[18],"bottleneck":[20],"many":[22],"iterative":[23],"sparse":[24],"matrix":[25,110],"solvers":[26],"like":[27,45],"CG":[28],"GMRES.":[30,143],"Here":[31],"k":[32,39,89,120],"iterations":[33,90],"conventional":[36],"implementation":[37,146],"perform":[38,88],"sparse-matrix-vector-multiplications":[40],"\u03a9(k)":[42,57],"vector":[43],"operations":[44],"dot":[46],"products,":[47],"resulting":[48],"that":[51],"grows":[52],"by":[53,91],"factor":[55],"both":[59],"network.":[63],"By":[64],"reorganizing":[65,79],"sparse-matrix":[67],"kernel":[68],"to":[69,114,129,137,156],"compute":[70],"set":[72],"matrix-vector":[74],"products":[75],"at":[76],"once":[77],"rest":[81],"algorithm":[84],"accordingly,":[85],"we":[86],"can":[87],"sending":[92],"O(log":[93],"P)":[94,101],"messages":[95,102],"instead":[96,118],"O(k":[98],"\u00b7":[99],"log":[100],"on":[103,122,147],"parallel":[105],"machine,":[106],"reading":[108],"A":[111],"from":[112],"DRAM":[113],"cache":[115],"just":[116],"once,":[117],"times":[121],"sequential":[124],"machine.":[125],"This":[126],"reduces":[127],"minimum":[131],"possible.":[132],"We":[133],"combine":[134],"these":[135],"techniques":[136],"form":[138],"new":[140],"variant":[141],"Our":[144],"shared-memory":[145],"an":[148],"8-core":[149],"Intel":[150],"Clovertown":[151],"gets":[152],"speedups":[153],"up":[155],"4.3x":[157],"over":[158],"standard":[159],"GMRES,":[160],"without":[161],"sacrificing":[162],"convergence":[163],"rate":[164],"or":[165],"numerical":[166],"stability.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":15},{"year":2013,"cited_by_count":14},{"year":2012,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
